Factoring in 'Worst Loss' over trading simulations...

Discussions about the testing and simulation of mechanical trading systems using historical data and other methods. Trading Blox Customers should post Trading Blox specific questions in the Customer Support forum.
Post Reply
flare9x
Contributor
Contributor
Posts: 3
Joined: Sun Mar 12, 2017 7:33 am

Factoring in 'Worst Loss' over trading simulations...

Post by flare9x » Mon Mar 13, 2017 8:15 am

Hello

When talking about risk management, many people work out their profit factor..... win 300... loss 100 = 3/1.... win 200, lose 100 = 2/1.

What are the thoughts of factoring the worst loss and also position size?

It might looks like this (monte carlo)

=if random <win% + starting capital+ (Starting Capital x % invest) x (avg win / worst loss) -
(Starting capital x % invest) x (avg loss / worst loss)

This was the formula for running a monte carlo over your worst loss -

However, it is interesting as its taking a ratio of the avg win and loss and comparing to the worst loss - versus the traditional avg win / avg loss.

Any math geeks out there care to chime in what their thoughts about this is?

Tim Arnold
Site Admin
Site Admin
Posts: 8501
Joined: Tue Apr 06, 2004 1:41 pm
Location: Boston, MA
Contact:

Re: Factoring in 'Worst Loss' over trading simulations...

Post by Tim Arnold » Mon Mar 13, 2017 4:13 pm

I usually remove the outliers, top x winners and losers in my mind are likely not statistically significant for analysis. There is always some tail chance of a black swan event, but that is a different discussion.

Post Reply